Failure prediction method, device, equipment and medium for long-tail POI

Abstract

The present disclosure provides a method, apparatus, device, medium and program product for predicting the failure of long-tail POIs, which relates to the field of artificial intelligence technology, especially to the field of deep learning and computer vision technology, and can be applied to scenarios such as face image processing and face image recognition. The specific implementation scheme is: obtaining feature information of the long-tail POI to be predicted, wherein the feature information is related to the attributes of the long-tail POI; using a pre-trained prediction model, predicting the failure status of the long-tail POI to be predicted based on the feature information. Based on the pre-trained prediction model, the present disclosure predicts the failure status of a large number of long-tail POIs that have no intelligence to perceive based on the feature information of the long-tail POI, thereby ensuring the accuracy of the long-tail POI status.

Description

Technical Field

[0001] The present disclosure relates to the field of artificial intelligence technology, in particular to the field of deep learning and computer vision technology, and can be applied to scenarios such as face image processing and face image recognition, and specifically to a failure prediction method, device, equipment, medium and program product for long-tail POIs. Background Art

[0002] The accuracy of POI (Point of Interest) information in map data is extremely important. POI status information needs to be updated in a timely manner to provide users with a good search experience.

[0003] Over time, some POI data becomes large in size but rarely searched by users, becoming known as long-tail POIs. For these long-tail POIs, there's no effective intelligence available to determine if they're invalid. Therefore, to manage long-tail POI data and improve the accuracy of long-tail POI status information, timely identifying invalid POIs becomes a pressing issue. Summary of the Invention

[0004] The present disclosure provides a failure prediction method, apparatus, device, medium, and program product for long-tail POIs.

[0005] According to one aspect of the present disclosure, a failure prediction method for long-tail POIs is provided, comprising:

[0006] Acquire feature information of a long-tail POI to be predicted, wherein the feature information is related to an attribute of the long-tail POI;

[0007] The failure status of the long-tail POI to be predicted is predicted according to the feature information using a pre-trained prediction model.

[0008] According to another aspect of the present disclosure, a failure prediction device for a long-tail POI is provided, comprising:

[0009] A feature information acquisition module is used to acquire feature information of the long-tail POI to be predicted, wherein the feature information is related to the attributes of the long-tail POI;

[0010] The failure prediction module is used to predict the failure status of the long-tail POI to be predicted based on the feature information using a pre-trained prediction model.

[0011] According to another aspect of the present disclosure, there is provided an electronic device, comprising:

[0012] at least one processor; and

[0013] a memory communicatively connected to the at least one processor; wherein,

[0014] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the failure prediction method for the long-tail POI described in any embodiment of the present disclosure.

[0015] According to another aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable a computer to execute the failure prediction method for long-tail POIs according to any embodiment of the present disclosure.

[0016] According to another aspect of the present disclosure, a computer program product is provided, including a computer program. When the computer program is executed by a processor, the computer program implements the failure prediction method for the long-tail POI according to any embodiment of the present disclosure.

[0017] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The accompanying drawings are provided to facilitate a better understanding of the present invention and do not constitute a limitation of the present disclosure.

[0019] Figure 1 is a schematic diagram of a failure prediction method for a long-tail POI according to an embodiment of the present disclosure;

[0020] Figure 2 is a schematic diagram of a failure prediction method for a long-tail POI according to an embodiment of the present disclosure;

[0021] Figure 3 is a training process of a prediction model according to an embodiment of the present disclosure;

[0022] Figure 4 is a structural diagram of a failure prediction device for a long-tail POI according to an embodiment of the present disclosure;

[0023] Figure 5 4 is a block diagram of an electronic device for implementing the failure prediction method for long-tail POIs according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0024] The following description of exemplary embodiments of the present disclosure is made in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding. These details should be considered as merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0025] Figure 1 This is a flow chart of a failure prediction method for long-tail POIs according to an embodiment of the present disclosure. This embodiment is applicable to situations where the failure state of long-tail POIs is predicted by predicting the failure probability of long-tail POIs. It relates to the fields of artificial intelligence technology, especially deep learning and computer vision technology, and can be applied to scenarios such as face image processing and face image recognition. The method can be executed by a failure prediction device for long-tail POIs, which is implemented in software and / or hardware, and is preferably configured in an electronic device, such as a computer device or a server. Figure 1 As shown, the method specifically includes the following:

[0026] S101: Acquire feature information of a long-tail POI to be predicted, wherein the feature information is related to attributes of the long-tail POI.

[0027] S102: using a pre-trained prediction model, predicting the failure status of the long-tail POI to be predicted according to the feature information.

[0028] Long-tail POIs are large in data size and rarely searched by users, making it difficult to update their status through changes in POI intelligence or user reports. This disclosure extracts feature information related to the attributes of long-tail POIs and uses a pre-trained prediction model to predict the failure status of the long-tail POIs based on this feature information. For example, the prediction model can estimate the failure probability of a long-tail POI and then, based on a preset threshold, provide a prediction result indicating whether the long-tail POI is failed.

[0029] The feature information may be any information related to the attributes of the long-tail POI, such as the classification, location, and duration of the POI, and the present disclosure does not impose any limitation on this.

[0030] The technical solution of the disclosed embodiment trains a prediction model based on a machine learning method, and uses the prediction model to predict the failure status of a large number of long-tail POIs that have no intelligence to perceive based on feature information related to the attributes of long-tail POIs, thereby timely updating the status information of the POIs, achieving a high degree of accuracy, ensuring the accuracy of POI information, and improving the user's search experience.

[0031] Figure 2FIG. 1 is a flow chart of a method for predicting failure of long-tail POIs according to an embodiment of the present disclosure. This embodiment is further optimized based on the above embodiment. Figure 2 As shown, the method specifically includes the following:

[0032] S201: Acquire feature information of a long-tail POI to be predicted, wherein the feature information is related to attributes of the long-tail POI.

[0033] In one embodiment, the characteristic information may include at least one of the following: POI classification, city level, duration, whether it is located in a high-traffic area, number of user searches, online source, or POI coordinates.

[0034] Among them, the classification of POIs can include, for example, food, shopping, life services, tourist attractions, real estate and finance. Since the possibility of failure of long-tail POIs in different industries is different, the present disclosure uses the classification information of POIs as one of the feature information to predict the failure status of long-tail POIs; city levels can include first-tier cities, new first-tier cities, second-tier cities, etc. Generally speaking, the higher the city level, the greater the liquidity of merchants, because merchants with poor performance may find it difficult to afford high rents, so the city level can also be used as one of the feature information; the duration is the duration of the long-tail POI in the map database. Generally speaking, the longer the duration, the greater the failure probability of the long-tail POI, so the duration can also be used to predict the failure status of the long-tail POI; whether it is located in a high-traffic area, for example For example, it can include whether there are office buildings, shopping malls, subway stations and / or airports within the set range around the long-tail POI to be predicted. Generally speaking, long-tail POIs are located in business districts and public transportation hubs with high traffic flow, and their probability of failure is relatively low. Therefore, whether it is located in a high-traffic area is also used as one of the feature information; the number of user searches is the number of times users click on the query search results of the long-tail POI in applications such as map apps; the online source is the online source of the long-tail POI in the map data, which can be divided from the business latitude to distinguish the online channels of the POI, because the initial accuracy and subsequent maintenance of the online data of different channels are different; the POI coordinates can specifically be the coordinates of the long-tail POI after spherical projection of the longitude and latitude, which can be used to directly calculate the Euclidean distance, which is convenient for calculation.

[0035] In the above-mentioned feature information related to the attributes of long-tail POIs, different information contents are related to whether the long-tail POI is invalid. Therefore, by inputting these feature information into a pre-trained prediction model, the invalid status of the long-tail POI can be predicted.

[0036] S202: Binarize the feature information of whether the feature is located in a high-heat human flow area.

[0037] S203: Dumb coding is performed on the POI classification and the city level in the feature information.

[0038] S204: Perform logarithmic function transformation on the duration and the number of user searches in the feature information, and perform maximum value normalization on the result of the logarithmic function transformation.

[0039] S205 : Mapping the POI coordinates to a grid of a preset size, wherein the grid numbers are used as inputs of a prediction model.

[0040] The above operations S202-S205 all belong to feature processing. Through a series of feature processing, the processed feature information is input into the prediction model, which allows the prediction model to make better predictions and also allows the model to better learn features during the model training stage.

[0041] Specifically, in S202, the feature information regarding whether a location is located in an area with high foot traffic can be broken down into four binary features: whether there are office buildings, shopping malls, subway stations, and / or airports within a set range around the long-tail POI. These binary features are then input into the prediction model for processing. Clearly, this disclosure is also applicable to other areas with high foot traffic.

[0042] In S203, taking POI classification as an example, since POI classification is a discrete feature, if this feature is passed into the prediction model as a discrete value, there will be more than a dozen qualitative values, and this discrete value is not conducive to model parameter adjustment and model understanding. Therefore, for discrete features such as POI classification and city level in the feature information, the discrete feature can be expanded into N features. When the original feature value is the i-th qualitative value, the i-th extended feature is assigned a value of 1, and the other extended features are assigned a value of 0. Compared with the method of directly specifying discrete values, this can reduce the difficulty of subsequent parameter adjustment, and when the prediction model is a linear model GBDT (Gradient Boosting Decision Tree), the use of dummy-coded features can also achieve nonlinear effects.

[0043] In S204, in order to improve the prediction model's understanding of important features, continuous or nearly continuous features such as duration and number of user searches in the feature information are logarithmically transformed, and the results of the logarithmic transformation are normalized to the maximum value.

[0044] In S205, the POI coordinates are mapped to a grid of a preset size, and the grid numbers are used as inputs to the prediction model. By grid transformation, the speed of feature fitting by the prediction model can be improved without affecting the effectiveness of the prediction model itself.

[0045] S206 : Using the pre-trained prediction model, predict the failure status of the long-tail POI to be predicted based on the feature information.

[0046] The prediction model can be trained based on statistical machine learning methods, for example, it can be a linear model GBDT.

[0047] Furthermore, for the features of the POI coordinates after grid conversion, the correlation between the X and Y axes of the POI coordinates can be fitted at the input layer of the prediction model, for example, by using a polynomial transformation. Because the coordinates (X, Y) appear in pairs, fitting the correlation between the X and Y axes can enhance the prediction model's understanding of these features, subsequently improving the model's prediction performance.

[0048] The technical solution of the disclosed embodiments uses a machine learning-based prediction model to train a prediction model. Using this prediction model, based on feature information related to long-tail POI attributes, it can predict the failure status of a large number of long-tail POIs for which no intelligence is available, thereby ensuring timely updates of long-tail POI status. Furthermore, by performing a series of feature processing on the feature information, the model's understanding of the features is enhanced, improving the model's prediction accuracy, ensuring the accuracy of POI information, and enhancing the user's search experience.

[0049] Figure 3 This is the training process of the prediction model according to the embodiment of the present disclosure. This embodiment is further optimized based on the above embodiment. Figure 3 As shown in Figure 2, the training process specifically includes the following:

[0050] S301: Acquire historical data of multiple invalid long-tail POIs as training samples, wherein each training sample has invalid or valid labeling information.

[0051] The invalid long-tail POI can be determined as follows: if the signboard image of the target POI collected at the same geographical location as the target POI disappears, the target POI is determined to be an invalid long-tail POI.

[0052] S302: Extract feature information of each invalid long-tail POI from historical data.

[0053] The characteristic information includes at least one of the following: POI classification, city level, duration, whether it is located in a high-traffic area, number of user searches, online source or POI coordinates.

[0054] S303: Taking the feature information of each invalid long-tail POI as model input, taking the corresponding annotation information as model output, and performing model training on a binary classification task to obtain the prediction model.

[0055] The technical solution of the disclosed embodiment trains a prediction model based on a machine learning method, and uses the prediction model to predict the failure status of a large number of long-tail POIs that have no intelligence to perceive based on feature information related to the attributes of long-tail POIs, thereby timely updating the status information of the POIs, achieving a high degree of accuracy, ensuring the accuracy of POI information, and improving the user's search experience.

[0056] Figure 4 This is a schematic diagram of the structure of the failure prediction device for long-tail POI according to an embodiment of the present disclosure. This embodiment can be applied to the situation where the failure state of long-tail POI is predicted by predicting the failure probability of long-tail POI. It relates to the field of artificial intelligence technology, especially to the field of deep learning and computer vision technology, and can be applied to scenarios such as face image processing and face image recognition. The device can implement the failure prediction method for long-tail POI described in any embodiment of the present disclosure. Figure 4 As shown, the device 400 specifically includes:

[0057] A feature information acquisition module 401 is used to acquire feature information of a long-tail POI to be predicted, wherein the feature information is related to the attributes of the long-tail POI;

[0058] The failure prediction module 402 is configured to use a pre-trained prediction model to predict the failure status of the long-tail POI to be predicted according to the feature information.

[0059] Optionally, the device further includes a model training module, specifically configured to:

[0060] Obtain historical data of multiple expired long-tail POIs as training samples, where each training sample has annotated information of whether it is expired or extant;

[0061] Extracting feature information of each invalid long-tail POI from the historical data;

[0062] The feature information of each invalid long-tail POI is used as the model input, the corresponding annotation information is used as the model output, and the prediction model is obtained through model training of the binary classification task.

[0063] Optionally, the invalid long-tail POI is determined by:

[0064] If the signboard image of the target POI collected at the same geographical location as the target POI disappears, the target POI is determined to be an invalid long-tail POI.

[0065] Optionally, the characteristic information includes at least one of the following:

[0066] POI classification, city level, duration, whether it is located in a high-traffic area, number of user searches, online source or POI coordinates.

[0067] Optionally, whether the location is in a high-heat human traffic area includes:

[0068] Whether there are office buildings, shopping malls, subway stations and / or airports within the set range around the long-tail POI to be predicted.

[0069] Optionally, the device further includes a first feature processing module, configured to:

[0070] Before the failure prediction module uses the pre-trained prediction model to make a prediction, a binary processing is performed on the feature information as to whether the feature is located in a high-heat human flow area.

[0071] Optionally, the device further includes a second feature processing module, configured to:

[0072] Before the failure prediction module uses the pre-trained prediction model to make predictions, dummy coding is performed on the POI classification and the city level in the feature information.

[0073] Optionally, the device further includes a third feature processing module, configured to:

[0074] Before the failure prediction module uses the pre-trained prediction model to make predictions, a logarithmic function transformation is performed on the duration and the number of user searches in the feature information, and the result of the logarithmic function transformation is normalized to the maximum value.

[0075] Optionally, the device further includes a fourth feature processing module, configured to:

[0076] Before the failure prediction module uses the pre-trained prediction model to make predictions, the POI coordinates are mapped into a grid of a preset size, wherein the grid numbers are used as inputs to the prediction model.

[0077] Optionally, the input layer of the prediction model is at least used to fit the correlation between the X-axis and the Y-axis in the POI coordinates.

[0078] Optionally, the prediction model is trained based on a statistical machine learning method.

[0079] The above-mentioned product can execute the method provided by any embodiment of the present disclosure, and has the corresponding functional modules and beneficial effects of the execution method.

[0080] In the technical solutions disclosed herein, the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0081] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0082] Figure 5 A schematic block diagram of an example electronic device 500 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are provided as examples only and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0083] like Figure 5 As shown, the device 500 includes a computing unit 501, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 502 or a computer program loaded from a storage unit 508 into a random access memory (RAM) 503. Various programs and data required for the operation of the device 500 can also be stored in the RAM 503. The computing unit 501, the ROM 502, and the RAM 503 are connected to each other via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0084] Various components in device 500 are connected to I / O interface 505, including: an input unit 506, such as a keyboard, mouse, etc.; an output unit 507, such as various types of displays, speakers, etc.; a storage unit 508, such as a magnetic disk, optical disk, etc.; and a communication unit 509, such as a network card, modem, wireless communication transceiver, etc. The communication unit 509 allows device 500 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0085] The computing unit 501 can be various general-purpose and / or specialized processing components with processing and computing capabilities. Some examples of the computing unit 501 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various computing units that run machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The computing unit 501 performs the various methods and processes described above, such as the failure prediction method for long-tail POIs. For example, in some embodiments, the failure prediction method for long-tail POIs can be implemented as a computer software program tangibly embodied in a machine-readable medium, such as the storage unit 508. In some embodiments, part or all of the computer program can be loaded and / or installed onto the device 500 via the ROM 502 and / or the communication unit 509. When the computer program is loaded into the RAM 503 and executed by the computing unit 501, one or more steps of the failure prediction method for long-tail POIs described above can be performed. Alternatively, in other embodiments, the computing unit 501 may be configured to execute the failure prediction method for long-tail POIs in any other appropriate manner (for example, by means of firmware).

[0086] Various embodiments of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chip systems (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0087] The program code for implementing the method of the present disclosure can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device so that when the program code is executed by the processor or controller, the functions / operations specified in the flow chart and / or block diagram are implemented. The program code can be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0088] In the context of the present disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in conjunction with an instruction execution system, device or equipment. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium can include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0089] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0090] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0091] A computer system may include a client and a server. The client and server are typically remote from each other and typically interact via a communication network. This client-server relationship arises through computer programs running on the respective computers, creating a client-server relationship. The server may be a cloud server, also known as a cloud computing server or cloud host, a hosting product within the cloud computing service ecosystem that addresses the management difficulties and limited scalability of traditional physical hosting and VPS services. The server may also be a server in a distributed system or a server integrated with blockchain.

[0092] Artificial intelligence (AI) is the study of how computers can simulate certain human thought processes and intelligent behaviors (such as learning, reasoning, thinking, and planning). It encompasses both hardware and software technologies. AI hardware technologies generally include sensors, specialized AI chips, cloud computing, distributed storage, and big data processing. AI software technologies primarily encompass computer vision, speech recognition, natural language processing, machine learning / deep learning, big data processing, and knowledge graphs.

[0093] Cloud computing refers to a technology system that provides network access to elastically scalable shared pools of physical or virtual resources. These resources can include servers, operating systems, networks, software, applications, and storage devices, and can be deployed and managed on-demand in a self-service manner. Cloud computing technology provides efficient and powerful data processing capabilities for the application of technologies such as artificial intelligence and blockchain, as well as for model training.

[0094] It should be understood that the various forms of processes shown above can be used to reorder, add, or delete steps. For example, the steps described in this disclosure can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions provided by this disclosure can be achieved. This is not limited herein.

[0095] The above specific embodiments do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure shall be included within the scope of protection of this disclosure.

Claims

1. A failure prediction method for long-tail POIs, comprising: Obtaining feature information of the long-tail POI to be predicted, wherein the feature information is related to the attributes of the long-tail POI, including whether it is located in a high-traffic area, POI classification, city level, duration, number of user searches, and POI coordinates; Binarize the feature information regarding whether the POI is located in a high-traffic area; dummy-code the POI classification and the city level; perform logarithmic transformation on the duration and the number of user searches, and normalize the result of the logarithmic transformation; map the POI coordinates to a grid of a preset size, wherein the grid number serves as input to a pre-trained prediction model; The prediction model is used to predict the failure status of the long-tail POI to be predicted based on the feature information.

2. The method according to claim 1, wherein The training process of the prediction model includes: Obtain historical data of multiple expired long-tail POIs as training samples, where each training sample has annotated information of whether it is expired or extant; Extracting feature information of each invalid long-tail POI from the historical data; The feature information of each invalid long-tail POI is used as the model input, the corresponding annotation information is used as the model output, and the prediction model is obtained through model training of the binary classification task.

3. The method according to claim 2, wherein: The invalid long-tail POI is determined in the following way: If the signboard image of the target POI collected at the same geographical location as the target POI disappears, the target POI is determined to be an invalid long-tail POI.

4. The method according to claim 1 or 2, wherein: The feature information also includes the online source of the long-tail POI to be predicted in the map data.

5. The method according to claim 4, wherein Whether it is located in a high-heat traffic area includes: Whether there are office buildings, shopping malls, subway stations and / or airports within the set range around the long-tail POI to be predicted.

6. The method according to claim 4, wherein: The input layer of the prediction model is at least used to fit the correlation between the X-axis and the Y-axis in the POI coordinates.

7. The method according to claim 1, wherein The prediction model is trained based on statistical machine learning methods.

8. A failure prediction device for long-tail POIs, comprising: A feature information acquisition module is used to obtain feature information of the long-tail POI to be predicted, wherein the feature information is related to the attributes of the long-tail POI, and the feature information includes whether it is located in a high-traffic area, POI classification, city level, existence time, number of user searches, and POI coordinates; A first feature processing module is used to perform a binary processing on the feature information of whether the feature information is located in a high-heat human flow area; A second feature processing module is used to perform dummy coding on the POI classification and the city level to which it belongs; A third feature processing module is configured to perform a logarithmic function transformation on the duration and the number of user searches, and perform maximum value normalization on the result of the logarithmic function transformation; a fourth feature processing module, configured to map the POI coordinates into a grid of a preset size, wherein the grid numbers are used as input to a pre-trained prediction model; The failure prediction module is used to use the prediction model to predict the failure status of the long-tail POI to be predicted according to the feature information.

9. An electronic device comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor. The instructions are executed by the at least one processor to enable the at least one processor to execute the failure prediction method for the long-tail POI according to any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to enable a computer to execute the failure prediction method for a long-tail POI according to any one of claims 1 to 7.

11. A computer program product, comprising a computer program, wherein when executed by a processor, the computer program implements the failure prediction method for long-tail POI according to any one of claims 1 to 7.

Images